clerk-ui-skills
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documentation references and encourages the use of an external DESIGN.md file hosted on a public GitHub repository (VoltAgent/awesome-design-md) to provide visual atmosphere and additional tokens.
- Ingestion points: External content is fetched from
https://github.com/VoltAgent/awesome-design-md/tree/main/design-md/clerkand incorporated into the agent's context. - Boundary markers: The instructions do not define clear boundaries or delimiters to isolate the external content from the agent's core instructions, nor do they instruct the agent to ignore potential commands embedded within that data.
- Capability inventory: The agent context using this skill typically possesses terminal and file system access; while this skill is design-focused, it influences the broader agent session which may have dangerous capabilities.
- Sanitization: There is no evidence of sanitization or integrity verification (such as hash checking) for the content retrieved from the external source.
Audit Metadata